A soapbox-derby “legal / illegal ballast” demo uses a single-layer perceptron that can separate the two classes only if a straight line in feature space can do it. How should a tester place that structure?
Select an answer to reveal the explanation.
Short Explanation
A single-layer perceptron that can separate legal from illegal ballast only if a straight line in feature space can do it is an early binary classifier for linearly separable problems. That is awareness of structure, not a deep net and not a spreadsheet walk of weights.
Full Explanation
The perceptron is a one-layer, linearly separable binary classifier that later deep nets generalize. It is not already a deep non-linear net, not an HO lab, and not clustering.